Image de couverture de livre

Grokking Beyond the Euclidean Norm of Model Parameters

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Notsawo, Pascal Jr Tikeng, Dumas, Guillaume, Rabusseau, Guillaume
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence I.2.6
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Grokking Finite-Dimensional Algebra
par: Notsawo, Pascal Jr Tikeng, et autres
Publié: (2026)

Benefits and Limitations of Communication in Multi-Agent Reasoning
par: Rizvi-Martel, Michael, et autres
Publié: (2025)

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
par: Yıldırım, Alper
Publié: (2026)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
par: Hedar, Abdel-Rahman, et autres
Publié: (2024)

Why Online Reinforcement Learning is Causal
par: Schulte, Oliver, et autres
Publié: (2024)

Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space
par: Mangannavar, Rajesh, et autres
Publié: (2024)

A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
par: Leyli-Abadi, Milad, et autres
Publié: (2026)

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
par: Abramov, Roman, et autres
Publié: (2025)

Large Language Models as Attribution Regularizers for Efficient Model Training
par: Vukadin, Davor, et autres
Publié: (2025)

Approximate Domain Unlearning for Vision-Language Models
par: Kawamura, Kodai, et autres
Publié: (2025)

Evaluating Model Explanations without Ground Truth
par: Rawal, Kaivalya, et autres
Publié: (2025)

Scaling Offline RL via Efficient and Expressive Shortcut Models
par: Espinosa-Dice, Nicolas, et autres
Publié: (2025)

Architectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt Detection
par: Noon, Jay
Publié: (2026)

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
par: Ribeiro, José, et autres
Publié: (2022)

A Practical Approach to using Supervised Machine Learning Models to Classify Aviation Safety Occurrences
par: Siow, Bryan Y.
Publié: (2025)

Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
par: Kohlberger, Björn Roman
Publié: (2026)

A Systematic Evaluation of Euclidean Alignment with Deep Learning for EEG Decoding
par: Junqueira, Bruna, et autres
Publié: (2024)

Model Fusion via Retrofitting
par: Luenam, Phoomraphee, et autres
Publié: (2025)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
par: Fadli, Samih
Publié: (2025)

AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites
par: Zhang, Qinshi, et autres
Publié: (2026)

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
par: Anderson, Samuel Cyrenius
Publié: (2026)

On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning
par: Deshmukh, Pratik, et autres
Publié: (2026)

Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models
par: Salla, Rohit Kumar, et autres
Publié: (2025)

Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
par: Heyman, Alex, et autres
Publié: (2025)

HEHRGNN: A Unified Embedding Model for Knowledge Graphs with Hyperedges and Hyper-Relational Edges
par: Rajagopalamenon, Rajesh, et autres
Publié: (2026)

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
par: Rath, Plawan Kumar, et autres
Publié: (2026)

Fusion-Based Neural Generalization for Predicting Temperature Fields in Industrial PET Preform Heating
par: Alsheikh, Ahmad, et autres
Publié: (2025)

The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback
par: Adapala, Sai Teja Reddy
Publié: (2025)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
par: Zhang, Xinyu
Publié: (2026)

I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
par: Thil, Lucas, et autres
Publié: (2025)

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
par: Liu, Weijie, et autres
Publié: (2025)

DataRater: Meta-Learned Dataset Curation
par: Calian, Dan A., et autres
Publié: (2025)

The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm
par: Birnick, Johann
Publié: (2025)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
par: Ha, SeungBum, et autres
Publié: (2025)

Residual Reservoir Memory Networks
par: Pinna, Matteo, et autres
Publié: (2025)

FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
par: Tian, Tian, et autres
Publié: (2025)

Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
par: Pinna, Matteo, et autres
Publié: (2025)

1 bit is all we need: binary normalized neural networks
par: Cabral, Eduardo Lobo Lustoda, et autres
Publié: (2025)

Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
par: Arora, Rushiv
Publié: (2025)

Global-Order GFlowNets
par: Pastor-Pérez, Lluís, et autres
Publié: (2025)